# Measuring Social Biases in Grounded Vision and Language Embeddings

arXiv: https://arxiv.org/abs/2002.08911 · HTML: https://mlsanity.com/paper/2002.08911/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

## Built on by (most cited first, 30 of 61)

- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study](https://mlsanity.com/paper/2303.17466/) (2023)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [MultiBench: Multiscale Benchmarks for Multimodal Representation Learning](https://mlsanity.com/paper/2107.07502/) (2021)
- [CM3: A Causal Masked Multimodal Model of the Internet](https://mlsanity.com/paper/2201.07520/) (2022)
- [ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension](https://mlsanity.com/paper/2204.05991/) (2022)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [Uncurated Image-Text Datasets: Shedding Light on Demographic Bias](https://mlsanity.com/paper/2304.02828/) (2023)
- [Modular Visual Question Answering via Code Generation](https://mlsanity.com/paper/2306.05392/) (2023)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization](https://mlsanity.com/paper/2410.16942/) (2024)
- [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021)
- [Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities](https://mlsanity.com/paper/2301.11100/) (2023)
- [On the Independence of Association Bias and Empirical Fairness in Language Models](https://mlsanity.com/paper/2304.10153/) (2023)
- [Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models](https://mlsanity.com/paper/2207.01056/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Would Deep Generative Models Amplify Bias in Future Models?](https://mlsanity.com/paper/2404.03242/) (2024)
- [MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models](https://mlsanity.com/paper/2303.12734/) (2023)
- [SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval](https://mlsanity.com/paper/2210.11773/) (2022)
- [Distribution-Aware Data Expansion with Diffusion Models](https://mlsanity.com/paper/2403.06741/) (2024)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP](https://mlsanity.com/paper/2408.10202/) (2024)
- [Model-Agnostic Gender Debiased Image Captioning](https://mlsanity.com/paper/2304.03693/) (2023)
- [New Job, New Gender? Measuring the Social Bias in Image Generation Models](https://mlsanity.com/paper/2401.00763/) (2024)

## Abstract (arXiv)

We generalize the notion of social biases from language embeddings to grounded vision and language embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This is despite the fact that vision and language can suffer from different biases, which one might hope could attenuate the biases in both. Multiple ways exist to generalize metrics measuring bias in word embeddings to this new setting. We introduce the space of generalizations (Grounded-WEAT and Grounded-SEAT) and demonstrate that three generalizations answer different yet important questions about how biases, language, and vision interact. These metrics are used on a new dataset, the first for grounded bias, created by augmenting extending standard linguistic bias benchmarks with 10,228 images from COCO, Conceptual Captions, and Google Images. Dataset construction is challenging because vision datasets are themselves very biased. The presence of these biases in systems will begin to have real-world consequences as they are deployed, making carefully measuring bias and then mitigating it critical to building a fair society.